He sat on the park bench, the newspaper crumpled in his hands. The air felt thick, heavy, as though he were breathing through cotton. The article, his meticulously researched and crafted piece on climate change, stared back at him from the printed page. His name was nowhere to be seen.

He stared at the headline, his jaw clenched. He felt a deep, twisting ache in his gut. Sunlight glinted off the passing cars, but he didn’t see them. He only saw the betrayal printed in bold black ink.

He crushed the paper tighter in his fist, the edges digging into his palm. He swallowed hard, trying to quell the rising tide of… something. He didn’t know how he was going to explain this to his family.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

This story is one of 1,000 stories generated for the emotion nervous. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 nervous stories, after denoising with neutral dialogue baselines, produces the nervous emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the nervous vector is projected through the unembedding matrix.

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210